Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    qualities of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edict
    0.68
     scatter
    0.66
     chubby
    0.65
     Radi
    0.63
     secre
    0.63
     dumbbells
    0.63
    ંત્રી
    0.62
     Dang
    0.62
     Scatter
    0.60
     patrol
    0.60
    POSITIVE LOGITS
     experience
    2.78
     Experience
    2.52
    Experience
    2.47
     experiences
    2.45
     experiência
    2.42
     experiencia
    2.40
    experience
    2.39
     experiencias
    2.27
     EXPERIENCE
    2.25
     expérience
    2.25
    Act Density 0.841%

    No Known Activations